{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:08:10Z","timestamp":1780492090113,"version":"3.54.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031975530","type":"print"},{"value":"9783031975547","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-97554-7_11","type":"book-chapter","created":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T01:00:09Z","timestamp":1751763609000},"page":"142-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Influence of\u00a0Mixed Precision on\u00a0Performance and\u00a0Accuracy of\u00a0DNN Training for\u00a0AI-Accelerated CFD Simulations on\u00a0NVIDIA Multi-GPU System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9116-8981","authenticated-orcid":false,"given":"Kamil","family":"Halbiniak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7345","authenticated-orcid":false,"given":"Krzysztof","family":"Rojek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1724-1786","authenticated-orcid":false,"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0004-1729","authenticated-orcid":false,"given":"Pawe\u0142","family":"Gepner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4020-5329","authenticated-orcid":false,"given":"Norbert","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"11_CR1","unstructured":"Abadi, M., et\u00a0al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of 12th USENIX Conference on Operating Systems Design and Implementation, pp. 265\u2013283 (2016)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Barbera, A.G., et\u00a0al.: AI-Driven Acceleration of Computational Fluid Dynamic Simulations. In: PPAM 2025. LNCS, vol. 15580 (in print) (2025)","DOI":"10.1007\/978-3-031-85703-4_7"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Ben-Nun, T., Hoefler, T.: Demystifying parallel and distributed deep learning: an in-depth concurrency analysis. ACM Comput. Surv. 52(4) (2019)","DOI":"10.1145\/3320060"},{"key":"11_CR4","first-page":"399","volume":"17","author":"G Calzolari","year":"2024","unstructured":"Calzolari, G., Liu, W.: Deep learning to develop zero-equation based turbulence model for CFD simulations of the built environment. Indoor\/Outdoor Airflow Air Qual. 17, 399\u2013414 (2024)","journal-title":"Indoor\/Outdoor Airflow Air Qual."},{"key":"11_CR5","unstructured":"Helios supercomputer. https:\/\/www.cyfronet.pl\/en\/19951,artykul,helios_super computer.html (2024)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"D\u00f6rrich, M., Fan, M., Kist, A.M.: Impact of mixed precision techniques on training and inference efficiency of deep neural networks. IEEE Access 11 (2023)","DOI":"10.1109\/ACCESS.2023.3284388"},{"key":"11_CR7","unstructured":"Intel Gaudi 3 AI Accelerator White Paper (2024). https:\/\/www.intel.com\/content\/ www\/us\/en\/content-details\/817486\/intel-gaudi-3-ai-accelerator-white-paper.html"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Halbiniak, K., Rojek, K., Iserte, S., Wyrzykowski, R.: Unleashing the Potential of Mixed Precision in AI-Accelerated CFD Simulation on Intel CPU\/GPU Architectures. In: ICCS 2024, LNCS, vol. 14837, 213\u2013217 (2024)","DOI":"10.1007\/978-3-031-63778-0_15"},{"key":"11_CR9","unstructured":"He, X., Sun, J., Chen, H., Li, D.: Campo: cost-aware performance optimization for mixed-precision neural network training. In: 2022 USENIX Annual Technical Conference (USENIX ATC 22), pp. 505\u2013518 (2022)"},{"key":"11_CR10","unstructured":"Introduction to PyTorch. https:\/\/pytorch.org\/tutorials\/beginner\/basics\/intro. html (2024)"},{"key":"11_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2022.101741","volume":"62","author":"S Iserte","year":"2022","unstructured":"Iserte, S., et al.: Accelerating urban scale simulations leveraging local spatial 3D structure. J. Comput. Sci. 62, 101741 (2022)","journal-title":"J. Comput. Sci."},{"key":"11_CR12","unstructured":"Kalamkar, D., et\u00a0al.: A study of bfloat16 for deep learning training. arXive preprint (2019). https:\/\/arxiv.org\/abs\/1905.12322"},{"key":"11_CR13","unstructured":"NVIDIA GH200 Grace Hopper Superchip Architecture (2024). https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Obiols-Sales, O., et\u00a0al.: CFDNet: a deep learning-based accelerator for fluid simulations. In: Proceedings of 34th ACM International Conference on Supercomputing, pp. 1\u201312 (2020)","DOI":"10.1145\/3392717.3392772"},{"key":"11_CR15","unstructured":"OpenFOAM Foundation: https:\/\/openfoam.org (2025). Accessed 20 Jan 2025"},{"key":"11_CR16","doi-asserted-by":"publisher","first-page":"21677","DOI":"10.1007\/s00521-022-07838-6","volume":"34","author":"D Panchigar","year":"2022","unstructured":"Panchigar, D., et al.: Machine learning-based CFD simulations: a review, models, open threats, and future tactics. Neural Comput. Appl. 34, 21677\u201321700 (2022)","journal-title":"Neural Comput. Appl."},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Rojek, K., Gepner, R.W.P.: Chemical mixing simulations with integrated AI accelerator. In: ICCS 2023. LNCS, vol. 14074, 494\u2013508 (2023)","DOI":"10.1007\/978-3-031-36021-3_50"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/978-3-031-31209-0_17","volume-title":"Euro-Par 2022: Parallel Processing Workshops","author":"K Rojek","year":"2023","unstructured":"Rojek, K., Wyrzykowski, R.: Performance and scalability analysis of AI-accelerated CFD simulations across various computing platforms. In: Singer, J., Elkhatib, Y., Heras, D., Diehl, P., Brown, N., Ilic, A. (eds.) Euro-Par 2022: Parallel Processing Workshops, pp. 223\u2013234. Springer International Publishing, Cham (2023)"},{"key":"11_CR19","unstructured":"Sadrehaghighi, I.: Artificial Intelligence (AI) and Deep Learning for CFD (2022). https:\/\/www.researchgate.net\/publication\/339795951"},{"key":"11_CR20","unstructured":"Sergeev, A., Balso, M.D.: Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint (2018). https:\/\/arxiv.org\/abs\/1802.05799"},{"key":"11_CR21","unstructured":"Shallue, C.J., et\u00a0al.: Measuring the Effects of Data Parallelism on Neural Network Training. arXiv preprint (2019). https:\/\/arxiv.org\/pdf\/1811.03600"},{"key":"11_CR22","unstructured":"Shen, L., et\u00a0al.: Pytorch distributed: experiences on accelerating data parallel training. arXive preprint (2020). https:\/\/arxiv.org\/abs\/2006.15704"},{"key":"11_CR23","unstructured":"Srivastava, S., Damodaran, M., Khoo, B.C.: Machine Learning Surrogates for Predicting Response of an Aero-structural-sloshing System (2019). https:\/\/arxiv.org\/pdf\/1911.10043"},{"key":"11_CR24","unstructured":"Tschannen, M., Bachem, O., Lucic, M.: Recent advances in autoencoder-based representation learning. arXive preprint (2018). https:\/\/arxiv.org\/pdf\/1812.05069"},{"key":"11_CR25","unstructured":"Versteeg, H.K., Malalasekera, W.: An Introduction to Computational Fluid Dynamics: The Finite Volume Method. Pearson Education (2007)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Vinuesa, R., Brunton, S.L.: The Potential of Machine Learning to Enhance Computational Fluid Dynamics. arXive preprint (2021). https:\/\/arxiv.org\/pdf\/2110.02085","DOI":"10.52843\/cassyni.nn3m2c"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Wu, X., et\u00a0al.: Performance, energy, and scalability analysis and improvement of parallel cancer deep learning candle benchmarks. In: ICPP 2019: Proceedings of the 48th International Conference on Parallel Processing. ACM (2019)","DOI":"10.1145\/3337821.3337905"},{"key":"11_CR28","unstructured":"Zhu, M., Bazaga, A., Lio, P.: Fluid-LLM: Learning computational fluid dynamics with spatiotemporal-aware large language models. arXive preprint (2024). https:\/\/arxiv.org\/abs\/2406.04501"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97554-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T01:44:26Z","timestamp":1778291066000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97554-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031975530","9783031975547"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97554-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}